To address the limitations of existing encrypted traffic classification methods, which suffer from insufficient feature representation and fine-grained analysis for critical business traffic, a Traffic mapping matrix (TMM)-based method is proposed. The TMM, integrating packet sequence features, statistical features, and topological structure features, is construct to create a composite representation with spatiotemporal correlations. A self-supervised classifier is designed based on the Vision Transformer architecture, and a pre-training framework is adopted to learn features from the TMM, thereby establishing the application behavior classification model (ABC-Model). Experimental results on both public and private datasets demonstrate that the proposed method achieves the highest accuracy of 96.73% in fine-grained application behavior classification. This study confirms that the multidimensional feature fusion of TMM effectively characterizes encrypted traffic behavior, providing a novel solution for critical business traffic identification.
PAPADOGIANNAKIE, IOANNIDISS. A survey on encrypted network traffic analysis applications, techniques, and countermeasures[J]. ACM Computing Surveys, 2021,54(6):1-35.
[2]
ZHAOR J, DENGX W, YANZ C, et al. Mt-flowformer: a semi-supervised flow transformer for encrypted traffic classification[C]∥Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York, USA: ACM,2022:2576-2584.
[3]
XIEK, XIER T, WANGX, et al. NMMF-stream: a fast and accurate stream-processing scheme for network monitoring data recovery[C]∥Proceedings of the IEEE INFOCOM 2022-IEEE Conference on Computer Communications. Piscataway, USA: IEEE, 2022:2218-2227.
[4]
FANJ Y, GUANC W, RENK, et al. Middlebox-based packet-level redundancy elimination over encrypted network traffic[J]. IEEE/ACM Transactions on Networking, 2018,26(4):1742-1753.
[5]
HEK M, CHENX L, XIES N, et al. Masked autoencoders are scalable vision learners[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, USA: IEEE, 2022:16000-16009.
[6]
CARONM, TOUVRONH, MISRAI, et al. Emerging properties in self-supervised vision transformers[C]∥Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway, USA: IEEE, 2021:9650-9660.
[7]
CHENX L, XIES N, HEK M. An empirical study of training self-supervised vision transformers[C]∥Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway, USA: IEEE, 2021:9640-9649.
[8]
ZHAOR J, DENGX W, WANGY H, et al. GeeSolver: a generic, efficient, and effortless solver with self-supervised learning for breaking text captchas[C]∥Proceedings of the 2023 IEEE Symposium on Security and Privacy. Piscataway, USA: IEEE, 2023:1649-1666.
[9]
DEVLINJ, CHANGM W, LEEK, et al. BERT: pre-training of deep bidirectional transformers for language understanding[C]∥Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Stroudsburg, USA: ACL, 2019:4171-4186.
[10]
ZHAOR J, ZHANM W, DENGX W, et al. A novel self-supervised framework based on masked autoencoder for traffic classification[J]. IEEE/ACM Transactions on Networking, 2024,32(3):2012-2025.
[11]
PANCHENKOA, LANZEF, PENNEKAMPJ, et al. Website fingerprinting at internet scale[C]∥Proceedings of Network and Distributed System Security Symposium. San Diego, USA: ISOC, 2016. DOI:10.14722/ndss.2016.23477 .
[12]
TAYLORV F, SPOLAORR, CONTIM, et al. Appscanner: automatic fingerprinting of smartphone apps from encrypted network traffic[C]∥Proceedings of the 2016 IEEE European Symposium on Security and Privacy. Piscataway, USA: IEEE, 2016:439-454.
[13]
FUC P, LIQ, XUK. Detecting unknown encrypted malicious traffic in real time via flow interaction graph analysis[DB/OL]. (2023-01-31)[2025-03-19].
[14]
LIUC, HEL T, XIONGG, et al. Fs-net: a flow sequence network for encrypted traffic classification[C]∥Proceedings of the IEEE INFO-COM 2019-IEEE Conference on Computer Communications. Piscataway, USA: IEEE, 2019:1171-1179.
[15]
ACETOG, CIUONZOD, MONTIERIA, et al. MIMETIC: mobile encrypted traffic classification using multimodal deep learning[J]. Computer Networks, 2019,165:No.106944.
[16]
WANGX, CHENS, SUJ. App-net: a hybrid neural network for encrypted mobile traffic classification[C]∥Proceedings of the IEEE INFOCOM 2020-IEEE Conference on Computer Communications Workshops. Piscataway, USA: IEEE, 2020:424-429.
[17]
LIUB Q, CHENX, YUANQ J, et al. TMC-GCN: encrypted traffic mapping classification method based on graph convolutional networks[J]. Computers, Materials & Continua, 2025,82(2):3179-3201.
[18]
DRAPER-GILG, LASHKARIA H, MAMUNM S I, et al. Characterization of encrypted and VPN traffic using time-related features[C]∥Proceedings of the 2nd International Conference on Information Systems Security and Privacy. Setúbal, Portugal: SciTePress, 2016:407-414.
[19]
LASHKARIA H, DRAPER-GILG, MAMUNM S I, et al. Characterization of tor traffic using time based features[C]∥Proceedings of the 2nd International Conference on Information Systems Security and Privacy. Setúbal, Portugal: SciTePress, 2017,2:253-262.
[20]
SIRINAMP, IMANIM, JUAREZM, et al. Deep fingerprinting: undermining website fingerprinting defenses with deep learning[C]∥Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security. New York, USA: ACM, 2018:1928-1943.
[21]
SHAPIRAT, SHAVITTY. FlowPic: a generic representation for encrypted traffic classification and applications identification[J]. IEEE Transactions on Network and Service Management, 2021,18(2):1218-1232.